1. Hwajung Lee

2. Maximilien Brice, © CERN

3.  Fact: Processor population is exploding. Technology has dramatically reduced the price of processors.  Geographic distribution of processes  Resource sharing as used in P2P networks  Computation speed up (as in a grid)  Fault tolerance

4.  A network of processes/resources.  The nodes are processes/resources, and the edges are communication channels.

5.  The logical distribution of functional capabilities  Multiple processes  Interprocess communication  Disjoint address space  Collective goal

6.  Don’t hold your breath:  Biocomputing  Nanocomputing  Quantum computing ……  It all boils down to…  Divide-and-conquer  Throwing more hardware at the problem Reference: Lecture Note by Jimmy Lin, Univ. of Maryland

7. “Work” w1w1 w2w2 w3w3 r1r1 r2r2 r3r3 “Result” “worker” Partition Combine Reference: Lecture Note by Jimmy Lin, Univ. of Maryland

8.  Different threads in the same core  Different cores in the same CPU  Different CPUs in a multi-processor system  Different machines in a distributed system Reference: Lecture Note by Jimmy Lin, Univ. of Maryland

9.  Commodity vs. “exotic” hardware  Number of machines vs. processor vs. cores  Memory vs. disk vs. network bandwidth  Different programming models Reference: Lecture Note by Jimmy Lin, Univ. of Maryland

10. Client-server modelPeer-to-peer model

11.  In both parallel and distributed systems, the events are partially ordered.  In parallel systems, the primarily issue is speed-up  In distributed systems the primary issues are fault- tolerance and availability of services

12.  Internet banking  Web search  Net meeting  Distance education  Internet auction  Google earth  Google sky  And so on…

13.  Large networks are very commonplace these days. Think of the world wide web. Other examples are:  Ubiquitous Computing  Cloud computing  Grid computing, Grid computing networks ▪ Ex. Computational grids (OSG, Teragrid, SETI@home)  Sensor networks  Network of mobile robots  And so on…

14. Checking the structural integrity

16. Image Source: www.vemurivenkatrao.com/nature/cloud/

17.  Knowledge is local  Clocks are not synchronized  No shared address space  Topology and routing  Scalability  Fault tolerance

18.  Leader election  Mutual exclusion  Time synchronization  Distributed snapshot  Replica management

19.  Understand how a system works, why it fails, and how we can guarantee our design.  We are not discussing implementation or programming, although they are also important issues

20.  Practical distributed systems must have a real network as its backbone. However, such systems can be simulated on a shared-memory multiprocessor, or even on a uniprocessor.